Helpers

Message History

The Message History component provides combined chat history and message storage functionality. It can store and retrieve chat messages from either Robility flow storage or a dedicated chat memory database like Mem0 or Redis.

It replaces the legacy Chat History and Message Store components.

Important: 

The Language Model and Agent components have built-in chat memory that is enabled by default and uses Robility flow storage.

This built-in chat memory functionality is sufficient for most use cases.

Use the Message History component only if you need to access chat memories outside the chat context, such as sentiment analysis flow that retrieves and analyzes recently stored memories, or you want to store memories in a specific database, separate from Robility flow storage.

For more information, see Store chat memory.

Use the Message History component in a flow

The Message History component has two modes, depending on where you want to use it in your flow:

a. Retrieve mode: The component retrieves chat messages from your Robility flow database or external memory.

b. Store mode: The component stores chat messages in your Robility flow database or external memory.

This means that you need multiple Message History components in your flow if you want to both store and retrieve chat messages.

Use Robility flow storage

The following steps explain how to create a chat-based flow that uses Message History components to store and retrieve chat memory from your Robility flow installation’s database:

1. Create or edit a flow where you want to use chat memory.
2. At the beginning of the flow, add a Message History component, and then set it to Retrieve mode. 
3. Optional: In the Message History component’s header menu, click Controls to enable parameters for memory sorting, filtering, and limits. 
4. Add a Prompt Template component, add a {memory} variable to the Template field, and then connect the Message History output to the memory input.

The Prompt Template component supplies instructions and context to LLMs, separate from chat messages passed through a Chat Input component. The template can include any text and variables that you want to supply to the LLM, for example:

You are a helpful assistant that answers questions.

Use markdown to format your answer, properly embedding images and urls.

History:

{memory}Variables ({variable}) in the template dynamically add fields to the Prompt Template component so that your flow can receive definitions for those values from elsewhere, such as other components, Robility flow global variables, or runtime input.

In this example, the {memory} variable is populated by the retrieved chat memories, which are then passed to a Language Model or Agent component to provide additional context to the LLM.

5. Connect the Prompt Template component’s output to a Language Model component’s System Message input.

This example uses a Language Model component as the central chat driver, but you can also use an Agent component.

6. Add a Chat Input component and then connect it to the Language Model component’s Input input. 
7. Connect the Language Model component’s output to a Chat Output component. 
8. At the end of the flow, add another Message History component, and then set it to Store mode.

Configure any additional parameters in the second Message History component as needed, taking into consideration that this component will store chat messages rather than retrieve them.

9. Connect the Chat Output component’s output to the Message History component’s Message input.

Each response from the LLM is output from the Language Model component to the Chat Output component and then stored in chat memory by the final Message History component. 

Use external chat memory

To store and retrieve chat memory from a dedicated, external chat memory database, use the Message History component and a provider-specific chat memory component.

Available provider-specific chat memory components include Cassandra Chat Memory component, Mem0 Chat Memory component, and Redis Chat Memory component. For all provider-specific chat memory components, see Bundles.

The following steps explain how to create a flow that stores and retrieves chat memory from Redis chat memory:

1. Create or edit a flow where you want to use chat memory.
2. At the beginning of the flow, add Message History and Redis Chat Memory components:
3. Configure the Redis Chat Memory component to connect to your Redis database. For more information, see the Redis documentation.
4. Set the Message History component to Retrieve mode.
5. In the Message History component’s header menu, click Controls, enable External Memory, and then click Close.

In Controls, you can also enable parameters for memory sorting, filtering, and limits.

6. Connect the Redis Chat Memory component’s output to the Message History component’s External Memory input.
7. Add a Prompt Template component, add a {memory} variable to the Template field, and then connect the Message History output to the memory input.

The Prompt Template component supplies instructions and context to LLMs, separate from chat messages passed through a Chat Input component. The template can include any text and variables that you want to supply to the LLM, for example:

You are a helpful assistant that answers questions.

Use markdown to format your answer, properly embedding images and urls.

History:

{memory}Variables ({variable}) in the template dynamically add fields to the Prompt Template component so that your flow can receive definitions for those values from elsewhere, such as other components, Robility flow global variables, or runtime input.

In this example, the {memory} variable is populated by the retrieved chat memories, which are then passed to a Language Model or Agent component to provide additional context to the LLM.

8. Connect the Prompt Template component’s output to a Language Model component’s System Message input.

This example uses a Language Model component as the central chat driver, but you can also use an Agent component.

9. Add a Chat Input component and then connect it to the Language Model component’s Input input.
10. Connect the Language Model component’s output to a Chat Output component.
11. At the end of the flow, add another pair of Message History and Redis Chat Memory components:

a. Configure the Redis Chat Memory component to connect to your Redis database.
b. Set the Message History component to Store mode.
c. In the Message History component’s header menu, click Controls, enable External Memory, and then click Close.

Configure any additional parameters in this component as needed, taking into consideration that this particular component will store chat messages rather than retrieve them.

12. Connect the Redis Chat Memory component to the Message History component’s External Memory input.
13. Connect the Chat Output component’s output to the Message History component’s Message input.

Each response from the LLM is output from the Language Model component to the Chat Output component and then stored in chat memory by passing it to the final Message History and Redis Chat Memory components.

Message History parameters

Many Message History component input parameters are hidden by default in the visual editor. You can toggle parameters through the Controls in the component’s header menu.